INDEX

Explanations

coding comments or documentation in programming languages

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

Ãło

-0.14

iky

-0.14

uke

-0.14

Ð°ÑĤÐ¾Ð²

-0.14

ella

-0.14

herence

-0.14

GH

-0.13

.alibaba

-0.13

ÑįÑĤ

-0.13

 garn

-0.13

POSITIVE LOGITS

tsx

0.15

ritz

0.15

readystatechange

0.15

 disg

0.14

 Indies

0.14

vely

0.14

TODO

0.14

ORITY

0.14

Vu

0.14

angl

0.14

Activations Density 0.070%

coding comments or documentation in programming languages

No Comments

No Known Activations