INDEX

Explanations

references to teams and experts in various professional contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

gon

-0.15

 trá»¥

-0.14

rior

-0.14

ipe

-0.14

TF

-0.14

pector

-0.14

peer

-0.14

 Differential

-0.13

 MessageBoxButtons

-0.13

POSITIVE LOGITS

IGHL

0.16

 selves

0.15

deaux

0.15

rej

0.14

chs

0.14

chyb

0.14

)((((

0.14

oucher

0.14

ertz

0.14

	throws

0.13

Activations Density 0.272%

references to teams and experts in various professional contexts

No Comments

No Known Activations