INDEX

Explanations

programming-related function calls and return statements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

ä¿Ĭ

-0.15

rve

-0.15

Naz

-0.15

_Lean

-0.15

evin

-0.15

isoft

-0.15

Nonnull

-0.14

modifiable

-0.14

inspace

-0.14

assen

-0.14

POSITIVE LOGITS

0.23

 Integer

0.20

=-

0.19

(-

0.18

Integer

0.17

uzu

0.16

==-

0.16

npos

0.16

Activations Density 0.085%

programming-related function calls and return statements

No Comments

No Known Activations