INDEX

Explanations

punctuation marks and quotations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

_bulk

-0.15

ÑĥÐºÐ¸

-0.14

edList

-0.14

bulk

-0.14

rend

-0.14

bread

-0.14

Selectors

-0.14

 Scrolls

-0.13

 rend

-0.13

 bulk

-0.13

POSITIVE LOGITS

ROTO

0.18

 Pret

0.16

CTX

0.16

èĩ

0.14

PARSE

0.14

STE

0.14

');?>"

0.14

ADER

0.14

variants

0.13

ida

0.13

Activations Density 0.005%

punctuation marks and quotations

No Comments

No Known Activations