INDEX

Explanations

technical and programming-related terms pertaining to a software or logging system

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

PTS

-0.15

ÑĸÐ´Ñĥ

-0.14

ertos

-0.14

ãĤ·ãĤ¢

-0.14

rug

-0.14

rive

-0.14

icha

-0.14

èĬ¯

-0.13

VEC

-0.13

echa

-0.13

POSITIVE LOGITS

0.15

indir

0.14

uhn

0.14

ulen

0.14

anela

0.14

uge

0.14

Ĺ

0.13

Activations Density 0.059%

technical and programming-related terms pertaining to a software or logging system

No Comments

No Known Activations