INDEX

Explanations

terms related to software licensing and disclaimers

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

-d

-0.16

ilenames

-0.15

 Ð±ÑĥÐº

-0.14

 ngang

-0.14

kop

-0.14

wner

-0.14

ç«ĭãģ¦

-0.14

Í

-0.14

lep

-0.13

agra

-0.13

POSITIVE LOGITS

 Hubb

0.14

linger

0.14

aÃ±

0.14

Cols

0.14

Ã³nico

0.14

iegel

0.14

amel

0.13

ABS

0.13

rema

0.13

uen

0.13

Activations Density 0.010%

terms related to software licensing and disclaimers

No Comments

No Known Activations