INDEX

Explanations

references to peripheral neuropathy and related terms

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

íĦ°

-0.18

Ã¸y

-0.17

lient

-0.15

PÅĻi

-0.15

Doe

-0.14

 Ð²ÐµÑīÐµÑģÑĤÐ²

-0.14

oho

-0.14

iger

-0.14

iola

-0.14

 Ð¿ÑĢÐ°Ð²Ð¸Ð»Ð¾

-0.14

POSITIVE LOGITS

deaux

0.16

SEA

0.15

 drain

0.15

#ad

0.15

combe

0.15

0.14

anagan

0.14

/Index

0.14

 Public

0.14

pav

0.13

Activations Density 0.002%

references to peripheral neuropathy and related terms

No Comments

No Known Activations