INDEX

Explanations

terms related to political positions or stances

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

aeda

-0.15

isay

-0.15

Ã¡cil

-0.15

pedia

-0.15

Ã´te

-0.15

ween

-0.15

lena

-0.14

ongyang

-0.14

amedi

-0.14

POSITIVE LOGITS

.FontStyle

0.15

IBUT

0.15

STA

0.15

ãĤ«ãĥ«

0.14

.xtext

0.14

criptor

0.14

ee

0.14

Kom

0.14

 exemplary

0.14

æŁľ

0.14

Activations Density 0.007%

terms related to political positions or stances

No Comments

No Known Activations