INDEX

Explanations

references to specific locations or landmarks

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

RootElement

-0.19

 Emin

-0.17

aba

-0.14

 Seznam

-0.14

 âĹĦ

-0.14

lify

-0.14

pii

-0.14

_UD

-0.14

ogo

-0.13

POSITIVE LOGITS

/pages

0.15

yr

0.15

inh

0.15

Ã¤ter

0.14

ids

0.14

klad

0.14

åĲĳ

0.14

 teaching

0.14

 ranks

0.14

ulers

0.14

Activations Density 0.192%

references to specific locations or landmarks

No Comments

No Known Activations