INDEX

Explanations

technical or analytical references in the text

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

amo

-0.17

udur

-0.16

aight

-0.15

rani

-0.15

amik

-0.15

_ABS

-0.14

lauf

-0.14

otty

-0.14

leme

-0.14

letcher

-0.13

POSITIVE LOGITS

Ð°ÑĪÐ°

0.15

entai

0.15

icons

0.14

 Deng

0.14

berman

0.13

 Morrow

0.13

à¸±à¸Ħ

0.13

 Chang

0.13

íķŃ

0.13

itel

0.13

Activations Density 0.202%

technical or analytical references in the text

No Comments

No Known Activations