INDEX

Explanations

phrases indicating a sense of location or context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

 styl

-0.16

itan

-0.16

ippo

-0.15

 remot

-0.14

uke

-0.14

 Shorts

-0.14

roscope

-0.14

orious

-0.14

Ð»Ð¾ÑĢ

-0.14

ionic

-0.14

POSITIVE LOGITS

agli

0.16

dream

0.15

Ã¼ny

0.15

Tween

0.14

 Ð£ÐºÑĢÐ°ÑĹÐ½

0.14

jvu

0.13

ffffffff

0.13

ê¸Ī

0.13

dzi

0.13

Activations Density 0.010%

phrases indicating a sense of location or context

No Comments

No Known Activations