INDEX

Explanations

specific encoding formats or character sets in text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

Ä±rak

-0.18

çª

-0.16

igel

-0.16

arb

-0.15

 tess

-0.15

eer

-0.14

 rencont

-0.14

 surre

-0.14

ëĿ¼ìĿ´

-0.14

 Enum

-0.14

POSITIVE LOGITS

 stdClass

0.14

Unique

0.14

 Kent

0.14

iena

0.14

 UNIQUE

0.14

è´¨

0.14

islav

0.14

strup

0.13

unique

0.13

Activations Density 0.001%

specific encoding formats or character sets in text

No Comments

No Known Activations