INDEX

Explanations

references to method invocation or function calls within a programming context

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

ing

-0.17

rott

-0.15

Ð¬

-0.15

geist

-0.15

 hopefully

-0.14

erb

-0.14

ëį°

-0.14

...↵

-0.14

Jac

-0.14

ahan

-0.14

POSITIVE LOGITS

Äįel

0.17

executable

0.16

áº¡m

0.15

awah

0.15

orgen

0.15

ourg

0.14

.nih

0.14

urv

0.14

reau

0.14

Ð¨ÐĲ

0.14

Activations Density 0.011%

references to method invocation or function calls within a programming context

No Comments

No Known Activations