INDEX

Explanations

numerical data related to rankings and comparisons

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

-0.16

 Clips

-0.15

audio

-0.15

 audio

-0.15

 below

-0.15

 Audio

-0.14

 phon

-0.14

sam

-0.14

 separat

-0.14

POSITIVE LOGITS

ãĥ¼ãĥĸ

0.19

Comparable

0.15

sko

0.15

íĴį

0.15

æķ¦

0.15

ichte

0.14

_suite

0.14

/hooks

0.14

ãĥ¼ãĥ«

0.14

 peÅŁ

0.14

Activations Density 0.013%

numerical data related to rankings and comparisons

No Comments

No Known Activations