INDEX

Explanations

statements about the justification and implications of actions or beliefs

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

encent

-0.15

$MESS

-0.14

èī

-0.14

SystemService

-0.14

alar

-0.13

_AMD

-0.13

amik

-0.13

Extent

-0.13

izzo

-0.13

imens

-0.13

POSITIVE LOGITS

 odds

0.16

ãģıãĤĵ

0.15

seo

0.15

æľĿ

0.14

wik

0.14

US

0.14

.streaming

0.13

ogan

0.13

isl

0.13

sw

0.13

Activations Density 0.146%

statements about the justification and implications of actions or beliefs

No Comments

No Known Activations