INDEX

Explanations

be

np_max-act · gemini-2.0-flash

The neuron responds to evaluative, affect‐laden words describing pleasurable or exciting sexual experiences.

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

CppGenericClass

-0.07

.Mutable

-0.07

_LOC

-0.07

.bc

-0.06

_ie

-0.06

 startled

-0.06

_nd

-0.06

 чист

-0.06

ifetime

-0.06

ávající

-0.06

POSITIVE LOGITS

 tvar

0.07

GRAPH

0.07

.GraphicsUnit

0.07

’T

0.07

포츠

0.06

 printed

0.06

defense

0.06

 корол

0.06

prung

0.06

 sacked

0.06

Activations Density 0.025%

be

The neuron responds to evaluative, affect‐laden words describing pleasurable or exciting sexual experiences.

No Comments

No Known Activations

be

The neuron responds to evaluative, affect‐laden words describing pleasurable or exciting sexual experiences.

No Comments

No Known Activations