INDEX

Explanations

line breaks and formatting elements in code or structured text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

emark

-0.15

ohn

-0.15

afone

-0.15

Äįer

-0.14

)((((

-0.14

£

-0.14

++.

-0.14

upal

-0.14

ep

-0.14

ersion

-0.14

POSITIVE LOGITS

chio

0.17

ients

0.17

ãĥķãĥĪ

0.16

0.15

orsi

0.15

ÐµÑı

0.15

 paran

0.15

_EXIT

0.14

 glac

0.14

Activations Density 0.038%

line breaks and formatting elements in code or structured text

No Comments

No Known Activations