INDEX

Explanations

structures and definitions in programming or code-related contexts

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

aryl

-0.15

 Burl

-0.15

wake

-0.14

prar

-0.14

ubre

-0.14

Ð¾Ð²ÐµÑĢ

-0.14

gis

-0.14

Ð¾Ð²

-0.14

ripp

-0.14

orang

-0.13

POSITIVE LOGITS

à¸²à¸°

0.15

aat

0.15

urg

0.15

-transitional

0.14

lices

0.14

ll

0.14

elta

0.14

Subset

0.14

rev

0.14

 plain

0.14

Activations Density 0.006%

structures and definitions in programming or code-related contexts

No Comments

No Known Activations