INDEX

Explanations

Tables and structured information

np_max-act · gemini-2.0-flash

This neuron never activates on any input tokens—it appears to be effectively “dead” and does not detect any pattern.

oai_token-act-pair · o4-mini Triggered by @xinyanhu8

New Auto-Interp

Configuration

andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.11.hook_resid_post

Architecture

standard

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 зб

-0.06

 princ

-0.06

JNI

-0.06

ov

-0.06

 valide

-0.06

 swarm

-0.06

 sandy

-0.06

Sys

-0.06

Price

-0.06

ิด

-0.06

POSITIVE LOGITS

 đứ

0.06

 weren

0.06

 Loaded

0.06

-directed

0.06

ále

0.06

 emanc

0.06

	logging

0.06

(fd

0.06

 افر

0.06

.todos

0.06

Activations Density 0.007%

Tables and structured information

This neuron never activates on any input tokens—it appears to be effectively “dead” and does not detect any pattern.

No Comments

No Known Activations

Tables and structured information

This neuron never activates on any input tokens—it appears to be effectively “dead” and does not detect any pattern.

No Comments

No Known Activations