INDEX

Explanations

occurrences of the word "Glad" and various forms of the word "World."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

Ĵ

-0.18

å¥Ī

-0.18

 Giles

-0.16

ÂŃn

-0.16

abox

-0.16

 Lynn

-0.16

hy

-0.15

Hy

-0.15

é±

-0.15

POSITIVE LOGITS

eth

0.17

vÃ¡

0.15

bew

0.15

endet

0.15

Eth

0.15

ken

0.15

ovah

0.14

PTS

0.14

fol

0.14

turnstile

0.14

Activations Density 0.052%

occurrences of the word "Glad" and various forms of the word "World."

No Comments

No Known Activations