INDEX

Explanations

punctuation marks within 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 @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

 latter

-0.15

foy

-0.14

edy

-0.14

aÃ§

-0.14

reeze

-0.14

oise

-0.14

fname

-0.13

yn

-0.13

Synopsis

-0.13

-↵

-0.13

POSITIVE LOGITS

 there

0.18

we

0.17

there

0.16

Kem

0.16

aban

0.15

ONO

0.14

HITE

0.14

 ÙģØ¥ÙĨ

0.14

emez

0.14

ills

0.14

Activations Density 0.752%

punctuation marks within the text

No Comments

No Known Activations