INDEX

Explanations

references to congregations and related religious terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

quin

-0.15

uga

-0.15

aken

-0.15

icable

-0.14

æĤł

-0.14

ight

-0.14

uggage

-0.14

ÑģÑĤÐ¸ÐºÐ°

-0.14

et

-0.14

phasis

-0.13

POSITIVE LOGITS

estion

0.21

Cong

0.18

regation

0.18

rats

0.18

ÏĥÏĦÎ±Î½

0.17

 Cong

0.17

ault

0.17

0.16

Lik

0.16

Activations Density 0.018%

references to congregations and related religious terms

No Comments

No Known Activations