INDEX

Explanations

any references to email or login prompts

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

anzi

-0.17

 è°

-0.16

otty

-0.15

 å·

-0.15

anÃ§a

-0.14

ili

-0.14

kie

-0.14

kovÃ¡

-0.14

enny

-0.14

anky

-0.14

POSITIVE LOGITS

Obs

0.15

 protected

0.15

ab

0.14

dyby

0.14

 Reeves

0.14

 Giul

0.14

Hen

0.14

[js

0.14

 Newsletter

0.13

 Cand

0.13

Activations Density 0.005%

any references to email or login prompts

No Comments

No Known Activations