INDEX

Explanations

occurrences of the term "overs" in various contexts related to sports and performance

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

èħĲ

-0.15

sing

-0.15

Ø¨ØŃ

-0.14

uring

-0.14

ay

-0.14

 Hack

-0.13

.mybatisplus

-0.13

imar

-0.13

POSITIVE LOGITS

wig

0.17

uw

0.16

opa

0.16

kill

0.15

egin

0.15

Å¡ek

0.15

edith

0.15

hang

0.15

iginal

0.15

comes

0.14

Activations Density 0.014%

occurrences of the term "overs" in various contexts related to sports and performance

No Comments

No Known Activations