INDEX

Explanations

phrases suggesting contradictions or nuances in character or societal roles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

aggi

-0.15

 unfinished

-0.15

oka

-0.15

iaux

-0.14

Tro

-0.14

ient

-0.14

-0.13

sek

-0.13

POSITIVE LOGITS

 immune

0.59

inv

0.49

immune

0.46

 immunity

0.40

 bullet

0.39

Imm

0.39

imp

0.38

-imm

0.37

imm

0.36

 immun

0.34

Activations Density 0.359%

phrases suggesting contradictions or nuances in character or societal roles

No Comments

No Known Activations