INDEX

Explanations

and with

np_max-act · gemini-2.0-flash

The neuron detects words or short phrases that convey strong emotional reactions or states (e.g. fear, shame, excitement).

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

ırken

-0.07

李

-0.07

 volts

-0.07

設計

-0.06

dır

-0.06

jac

-0.06

 خدمت

-0.06

(sess

-0.06

(rows

-0.06

_observer

-0.06

POSITIVE LOGITS

 APPLY

0.08

_MAKE

0.07

_playlist

0.06

Limit

0.06

META

0.06

mis

0.06

Spirit

0.06

Object

0.06

]:=

0.06

(area

0.06

Activations Density 0.027%

and with

The neuron detects words or short phrases that convey strong emotional reactions or states (e.g. fear, shame, excitement).

No Comments

No Known Activations