INDEX

Explanations

quantitative data and statistics

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

ensen

-0.15

 Durant

-0.14

Ð½Ð¸ÑĨ

-0.14

.getElementsByClassName

-0.14

onde

-0.13

\grid

-0.13

isse

-0.13

bis

-0.13

here

-0.13

unes

-0.13

POSITIVE LOGITS

eut

0.15

0.14

SSERT

0.14

bsites

0.14

iot

0.14

ollo

0.14

ãĤ§

0.14

.Logf

0.13

\Eloquent

0.13

Activations Density 0.086%

quantitative data and statistics

No Comments

No Known Activations