INDEX

Explanations

syntactic structures and punctuation in code-like text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

Ã¡d

-0.17

icio

-0.16

ÑĽ

-0.15

olecular

-0.15

ãĢģãģ©ãģĨ

-0.14

Î³Î³ÎµÎ»

-0.14

orio

-0.14

uria

-0.14

Ã¡p

-0.14

ÐµÐ´Ð¸Ð½

-0.14

POSITIVE LOGITS

atre

0.15

asca

0.14

etz

0.14

emi

0.14

.Dto

0.14

 dissolution

0.14

etes

0.14

 Hass

0.14

 alongside

0.14

Activations Density 0.085%

syntactic structures and punctuation in code-like text

No Comments

No Known Activations