INDEX

Explanations

relationships and dependencies in data or code structures

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

eki

-0.14

raquo

-0.14

ptune

-0.13

\Factory

-0.13

cee

-0.13

ÑĢÐµÑĪ

-0.13

Duy

-0.13

 Pessoa

-0.13

icious

-0.13

.linkedin

-0.12

POSITIVE LOGITS

_SEG

0.14

 clown

0.13

atas

0.13

printStats

0.13

Âļ

0.12

.Span

0.12

.Generated

0.12

VEC

0.12

Å¾i

0.12

arel

0.12

Activations Density 0.082%

relationships and dependencies in data or code structures

No Comments

No Known Activations