INDEX

Explanations

phrases related to improvement and positive outcomes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

áºŃt

-0.15

-0.14

adaki

-0.14

appa

-0.13

ologi

-0.13

/repository

-0.13

rypton

-0.12

cru

-0.12

POSITIVE LOGITS

 results

0.87

results

0.73

 Results

0.72

-results

0.67

Results

0.66

 resultados

0.65

 RESULTS

0.64

_results

0.62

 outcomes

0.61

 rÃ©sultats

0.59

Activations Density 0.251%

phrases related to improvement and positive outcomes

No Comments

No Known Activations