INDEX

Explanations

punctuation marks and formatting used in written text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

ephir

-0.16

 jenter

-0.14

alis

-0.14

nothrow

-0.14

OfClass

-0.13

opus

-0.13

 /*!↵

-0.13

anou

-0.13

IGO

-0.13

assing

-0.13

POSITIVE LOGITS

 Revel

0.16

amik

0.13

 Seks

0.13

uffer

0.13

 flushed

0.12

 Flush

0.12

ÚĺÙĩ

0.12

edes

0.12

Bol

0.12

sburg

0.12

Activations Density 0.073%

punctuation marks and formatting used in written text

No Comments

No Known Activations