INDEX

Explanations

notes or warnings regarding auto-generated content

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

EC

-0.15

ff

-0.15

utes

-0.15

 fairness

-0.15

-0.14

op

-0.14

 bows

-0.14

util

-0.14

ES

-0.14

 CrossRef

-0.14

POSITIVE LOGITS

 SÃ¼r

0.17

 GENERATED

0.16

 brace

0.15

-eslint

0.15

OperationException

0.15

ocode

0.14

ATEGORIES

0.14

RegularExpression

0.14

Generated

0.14

Screens

0.14

Activations Density 0.019%

notes or warnings regarding auto-generated content

No Comments

No Known Activations