INDEX

Explanations

references to political figures and governmental authority

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

ften

-0.15

idth

-0.15

 odio

-0.14

anki

-0.13

 Function

-0.13

_TYP

-0.13

ichel

-0.13

aily

-0.13

ê´Ģ

-0.12

ãĥĲãĥ¼

-0.12

POSITIVE LOGITS

opt

0.31

 elect

0.30

 decide

0.28

 choose

0.28

 chose

0.26

 decided

0.26

 bother

0.25

 decides

0.24

 opts

0.24

 resort

0.24

Activations Density 0.154%

references to political figures and governmental authority

No Comments

No Known Activations