INDEX

Explanations

terms related to biography and autobiographical writing

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

ournaments

-0.15

phan

-0.14

 Bram

-0.13

otics

-0.13

 rent

-0.13

enstein

-0.13

 applyMiddleware

-0.13

amins

-0.13

imest

-0.13

ournal

-0.13

POSITIVE LOGITS

bi

0.90

bio

0.81

 biography

0.80

Bi

0.74

Bi

0.71

bio

0.70

bi

0.70

 Ð±Ð¸

0.70

 Biography

0.67

Bio

0.65

Activations Density 0.305%

terms related to biography and autobiographical writing

No Comments

No Known Activations