INDEX

Explanations

proper nouns, specifically names of individuals

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

ition

-0.15

Ì£

-0.15

timeofday

-0.14

uppe

-0.14

odafone

-0.14

ÅĻeb

-0.14

ãģĬãĤĬ

-0.14

nton

-0.14

 RectTransform

-0.13

aidu

-0.13

POSITIVE LOGITS

0.17

 Recomm

0.17

 Writes

0.16

Likes

0.16

Writes

0.15

(@

0.15

(@

0.15

atron

0.15

Activations Density 0.206%

proper nouns, specifically names of individuals

No Comments

No Known Activations