INDEX

Explanations

technical details and specifications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

ÃĹ↵↵

-0.15

á»Ł

-0.15

idon

-0.15

_QMARK

-0.14

Ð²ÐµÐ¹

-0.14

andler

-0.13

§

-0.13

Ã¤tt

-0.13

peat

-0.13

agne

-0.13

POSITIVE LOGITS

0.15

ĵåĲį

0.15

é

0.15

thrown

0.14

à¸¸à¹Ī

0.13

umeric

0.13

_flutter

0.13

 bÃ³ng

0.13

icamente

0.13

Activations Density 0.860%

technical details and specifications

No Comments

No Known Activations