INDEX

Explanations

expressions of surprise or notable accomplishments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

luv

-0.18

ailles

-0.16

atÃŃm

-0.16

chio

-0.15

modifiable

-0.14

 tÃŃm

-0.14

iple

-0.14

UNE

-0.13

 çģ

-0.13

odb

-0.13

POSITIVE LOGITS

 given

0.75

 considering

0.70

given

0.64

 Given

0.59

 Considering

0.56

Given

0.55

 GIVEN

0.52

Considering

0.52

_given

0.43

consider

0.38

Activations Density 0.493%

expressions of surprise or notable accomplishments

No Comments

No Known Activations