INDEX

Explanations

references to sources or citations 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 @ 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

isco

-0.17

aldi

-0.14

_allocate

-0.14

jian

-0.14

raquo

-0.14

ÑĨÐ¸Ðº

-0.14

 Grim

-0.14

ISCO

-0.14

ikan

-0.14

Ã©gor

-0.14

POSITIVE LOGITS

oogle

0.16

olis

0.16

ernet

0.15

\Bridge

0.15

erea

0.14

rito

0.14

atura

0.14

ilm

0.14

bau

0.14

0.13

Activations Density 0.035%

references to sources or citations in the text

No Comments

No Known Activations