INDEX

Explanations

function definitions and parameters, particularly regarding optional arguments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

Sar

-0.14

quiv

-0.13

iores

-0.13

pmat

-0.13

 subclass

-0.13

Yas

-0.13

Cyr

-0.13

 Purdue

-0.13

uncated

-0.13

oston

-0.13

POSITIVE LOGITS

 arguments

0.55

 argument

0.52

 Arguments

0.47

arguments

0.45

Arguments

0.45

 Argument

0.43

 args

0.43

argument

0.42

arg

0.42

Argument

0.40

Activations Density 0.302%

function definitions and parameters, particularly regarding optional arguments

No Comments

No Known Activations