INDEX

Explanations

terms related to support and connections within various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

 quad

-0.16

inkel

-0.16

_TYPED

-0.15

orama

-0.15

ë¥´ê³ł

-0.15

Pu

-0.14

readcr

-0.14

 Quad

-0.14

illow

-0.14

POSITIVE LOGITS

Ã¡lt

0.15

ableView

0.15

_EOL

0.15

-dat

0.14

æķ

0.14

 useClass

0.14

TargetException

0.14

mgr

0.14

ception

0.13

achu

0.13

Activations Density 0.000%

terms related to support and connections within various contexts

No Comments

No Known Activations