INDEX

Explanations

occurrences of the word "Holy" and its variations, indicating a focus on religious or sacred themes

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

alog

-0.16

usk

-0.16

ropolis

-0.15

alo

-0.15

bob

-0.15

chers

-0.15

arine

-0.14

ele

-0.14

pieces

-0.14

urse

-0.14

POSITIVE LOGITS

ewan

0.16

ammer

0.16

á»ĥn

0.15

inger

0.15

estroy

0.14

ilig

0.14

 discrepan

0.14

ÙĩØ§Ø±

0.14

èħ

0.14

amt

0.14

Activations Density 0.007%

occurrences of the word "Holy" and its variations, indicating a focus on religious or sacred themes

No Comments

No Known Activations