INDEX

Explanations

references to specific categorical data or numerical values

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

-0.18

↵

-0.18

-0.16

onto

-0.15

<<

-0.15

orch

-0.14

ient

-0.14

oute

-0.14

/sm

-0.14

ved

-0.14

POSITIVE LOGITS

 AppleWebKit

0.31

inha

0.15

æ£ĭçīĮ

0.14

edik

0.14

Ø§ÙĦÛĮ

0.14

ager

0.14

Zem

0.14

chl

0.14

ahl

0.14

|(

0.14

Activations Density 0.400%

references to specific categorical data or numerical values

No Comments

No Known Activations