INDEX

Explanations

references to limitations or restrictions in 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 @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

 barg

-0.17

alu

-0.17

oki

-0.15

_criteria

-0.14

mans

-0.14

yu

-0.14

ulu

-0.14

alus

-0.14

astically

-0.13

Tou

-0.13

POSITIVE LOGITS

 matter

0.29

 indeed

0.25

matter

0.23

aille

0.20

 Matter

0.20

oda

0.16

 Cham

0.16

for

0.15

 matters

0.15

Indeed

0.15

Activations Density 0.102%

references to limitations or restrictions in various contexts

No Comments

No Known Activations