INDEX

Explanations

references to podcasts and related listening experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

:Register

-0.15

ç§Ģ

-0.15

ItemImage

-0.15

ovenant

-0.15

andal

-0.14

ockets

-0.14

ipur

-0.14

lobals

-0.14

eniable

-0.14

etime

-0.14

POSITIVE LOGITS

som

0.15

 feeding

0.14

erken

0.14

 attend

0.14

NG

0.14

poke

0.14

Man

0.14

Activations Density 0.847%

references to podcasts and related listening experiences

No Comments

No Known Activations