INDEX

Explanations

references to all statistical and quantitative data

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

imer

-0.16

Pad

-0.15

_UNIT

-0.15

ANDLE

-0.15

æĬ¼

-0.15

oger

-0.15

 Sent

-0.15

Sent

-0.14

lse

-0.14

ogl

-0.14

POSITIVE LOGITS

 gross

0.15

$MESS

0.15

fid

0.14

amba

0.14

 namoro

0.14

 Clips

0.14

(Program

0.14

½

0.13

scale

0.13

 Erick

0.13

Activations Density 0.009%

references to all statistical and quantitative data

No Comments

No Known Activations