INDEX

Explanations

words and phrases that indicate a sense of progression or transitions in context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

eti

-0.17

Invoker

-0.17

igan

-0.15

icens

-0.14

kus

-0.14

ÑĢÐ¾Ð²Ð°

-0.14

 Weed

-0.14

olor

-0.14

aight

-0.14

_patch

-0.14

POSITIVE LOGITS

obel

0.16

 Shen

0.14

 Ø¹Ø±Ø¨

0.14

|array

0.14

 predecessor

0.14

decess

0.14

ervo

0.14

inand

0.14

ott

0.14

thood

0.14

Activations Density 0.023%

words and phrases that indicate a sense of progression or transitions in context

No Comments

No Known Activations