INDEX

Explanations

references to trial-related legal proceedings and outcomes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

 DÃ¼n

-0.18

 Reform

-0.15

uten

-0.15

áº·n

-0.15

 pact

-0.14

 Brennan

-0.14

voc

-0.14

ãģĳãĤĮãģ©

-0.14

 WaitForSeconds

-0.14

ocache

-0.14

POSITIVE LOGITS

 trial

0.71

 trials

0.63

trial

0.63

 Trial

0.56

 Trials

0.55

Trial

0.55

_trial

0.51

 trail

0.42

_trials

0.41

 tried

0.39

Activations Density 0.121%

references to trial-related legal proceedings and outcomes

No Comments

No Known Activations