INDEX

Explanations

mathematical equalities and inequalities

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

PELL

-0.16

OTES

-0.16

elas

-0.15

TON

-0.15

(Source

-0.14

wards

-0.14

inion

-0.14

CTR

-0.14

omik

-0.14

POSITIVE LOGITS

/=

0.14

Detach

0.14

erno

0.14

lsi

0.14

ilis

0.13

isos

0.13

itemId

0.13

hive

0.13

uba

0.13

 revision

0.13

Activations Density 0.059%

mathematical equalities and inequalities

No Comments

No Known Activations