INDEX

Explanations

references to specific scientific classifications and metrics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

à¤¼

-0.15

aucoup

-0.14

 hood

-0.14

RuleContext

-0.14

enas

-0.14

egin

-0.14

spath

-0.13

Ð¾Ð²Ð°ÑĢÐ¸

-0.13

sett

-0.13

azine

-0.12

POSITIVE LOGITS

_merged

0.15

ç·

0.14

/^(

0.14

ilg

0.14

fabs

0.14

celik

0.13

ylie

0.13

èĭ±éĽĦ

0.13

_graphics

0.13

 triangle

0.13

Activations Density 0.260%

references to specific scientific classifications and metrics

No Comments

No Known Activations