INDEX

Explanations

occurrences of numerical data and related statistics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

 Este

-0.15

xima

-0.14

 Bucc

-0.14

RC

-0.14

Wid

-0.14

ixin

-0.13

undred

-0.13

ãĤ¤ãĥ³ãĥĪ

-0.13

aired

-0.13

POSITIVE LOGITS

ØªØ¨

0.16

çµ

0.15

 Blind

0.15

annels

0.15

isches

0.14

Å¾e

0.14

 Matte

0.14

 éĢ

0.14

rosso

0.14

ourd

0.14

Activations Density 0.004%

occurrences of numerical data and related statistics

No Comments

No Known Activations