INDEX

Explanations

numerical and statistical references

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

idia

-0.16

OX

-0.15

Fade

-0.14

bre

-0.14

abilia

-0.14

 cord

-0.14

uns

-0.14

+[

-0.14

pedo

-0.14

ivor

-0.14

POSITIVE LOGITS

atham

0.17

 Ø¯Ùģ

0.16

tok

0.16

ãĥ³ãĤ¬

0.15

anged

0.15

letcher

0.15

iseum

0.15

annah

0.14

urn

0.14

Activations Density 0.329%

numerical and statistical references

No Comments

No Known Activations