INDEX

Explanations

connections and relationships within a structured context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

andle

-0.15

opp

-0.15

StringEncoding

-0.13

jang

-0.13

á»ĭ

-0.13

ANDLE

-0.13

ke

-0.13

ando

-0.13

hq

-0.12

 superv

-0.12

POSITIVE LOGITS

 composition

0.59

 makeup

0.56

 compose

0.56

 Composition

0.54

 composing

0.52

Composition

0.48

composition

0.48

compose

0.47

 make

0.47

 ÑģÐ¾ÑģÑĤÐ°Ð²

0.46

Activations Density 0.169%

connections and relationships within a structured context

No Comments

No Known Activations