INDEX

Explanations

references to fact-checking and political claims

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

mund

-0.16

 háº¡

-0.15

fur

-0.15

nod

-0.15

ichel

-0.14

Ã¸

-0.14

borg

-0.14

 Coin

-0.14

Ð¾ÑĤ

-0.14

 Ð¿Ñĥ

-0.14

POSITIVE LOGITS

ersonic

0.16

asa

0.15

à¸¡à¸²à¸£

0.15

 tamp

0.15

anners

0.15

ENCY

0.15

.hxx

0.15

ustum

0.15

aucoup

0.14

gang

0.14

Activations Density 0.007%

references to fact-checking and political claims

No Comments

No Known Activations