INDEX

Explanations

quotations and dialogue in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

croft

-0.15

ilden

-0.14

sse

-0.13

eydi

-0.13

askell

-0.13

ÌĪ

-0.12

 geÃ§en

-0.12

ÑĢÐ°Ð´Ð¸

-0.12

 háº¡ng

-0.12

agn

-0.12

POSITIVE LOGITS

idd

0.14

iani

0.14

ember

0.13

olik

0.13

 Erik

0.13

uter

0.13

 Feder

0.13

rais

0.12

sein

0.12

Ro

0.12

Activations Density 0.113%

quotations and dialogue in the text

No Comments

No Known Activations