INDEX

Explanations

mathematical terms and relationships, specifically in the context of equations and proofs

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

izoph

-0.14

erva

-0.13

iesen

-0.13

ortho

-0.13

ParameterValue

-0.13

erif

-0.13

-modules

-0.13

 Ø§ÙĦØ°Ùĩ

-0.13

/fw

-0.13

elt

-0.13

POSITIVE LOGITS

uty

0.19

htdocs

0.15

enda

0.14

ruz

0.14

 errs

0.14

 stylist

0.14

PIO

0.13

alle

0.13

ols

0.13

Activations Density 0.095%

mathematical terms and relationships, specifically in the context of equations and proofs

No Comments

No Known Activations