INDEX

Explanations

references to legal licenses and terms of use

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

/goto

-0.17

top

-0.16

 Resistance

-0.14

decltype

-0.14

deb

-0.14

Resistance

-0.14

 presum

-0.14

ched

-0.14

eneg

-0.14

 Gast

-0.14

POSITIVE LOGITS

oga

0.17

ovah

0.16

lash

0.15

.opend

0.15

ennen

0.15

0.14

orget

0.14

jury

0.14

Activations Density 0.007%

references to legal licenses and terms of use

No Comments

No Known Activations