INDEX

Explanations

conditional statements and discussions of consequences

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

 Geld

-0.16

uyÃªn

-0.15

azzi

-0.15

 mate

-0.15

Ig

-0.15

heimer

-0.14

ieu

-0.14

czy

-0.13

Ze

-0.13

baugh

-0.13

POSITIVE LOGITS

vor

0.17

erson

0.14

alker

0.14

í

0.14

èīº

0.14

liche

0.14

Wunused

0.14

ertest

0.13

recated

0.13

ABS

0.13

Activations Density 0.208%

conditional statements and discussions of consequences

No Comments

No Known Activations