INDEX

Explanations

each

np_max-act · gemini-2.0-flash

This neuron detects phrases that introduce repeated measurements or sample groups (e.g. “For each…,” “In each…,” “Each…”).

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 tuyệt

-0.07

 focusing

-0.07

CN

-0.06

 Gaussian

-0.06

subject

-0.06

bole

-0.06

_S

-0.06

 nrows

-0.06

travel

-0.06

感到

-0.06

POSITIVE LOGITS

 each

0.07

/stdc

0.07

udi

0.07

+#

0.06

 піс

0.06

.Framework

0.06

 genellikle

0.06

);↵↵↵↵

0.06

 entfer

0.06

coy

0.06

Activations Density 0.019%

each

This neuron detects phrases that introduce repeated measurements or sample groups (e.g. “For each…,” “In each…,” “Each…”).

No Comments

No Known Activations