INDEX

Explanations

occurrences of programming-related keywords, particularly import statements

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

Orm

-0.17

itori

-0.15

AFX

-0.15

 Shot

-0.14

 Gors

-0.14

ATOM

-0.14

 Needle

-0.14

ired

-0.14

ormap

-0.14

ÑĢÐ¾ÑģÑĤÐ¾

-0.14

POSITIVE LOGITS

veau

0.17

 trades

0.15

lac

0.15

 unin

0.14

 tally

0.14

ÏĦÎ¹Ïĥ

0.14

~>

0.14

ngen

0.14

 dirt

0.13

(^

0.13

Activations Density 0.005%

occurrences of programming-related keywords, particularly import statements

No Comments

No Known Activations