INDEX

Explanations

code-related elements and components such as imports and exports in programming scripts

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

arios

-0.15

pedo

-0.14

inkel

-0.14

DITION

-0.14

 McCabe

-0.14

rance

-0.14

nia

-0.14

pread

-0.13

izon

-0.13

 dynam

-0.13

POSITIVE LOGITS

Å¯r

0.16

0.15

vat

0.15

orns

0.14

reso

0.14

 loin

0.14

 Mane

0.14

ÏģÎ¹Ïĥ

0.13

gee

0.13

oro

0.13

Activations Density 0.013%

code-related elements and components such as imports and exports in programming scripts

No Comments

No Known Activations