INDEX

Explanations

proper nouns related to people, places, and organizations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

ibaba

-0.15

ä¸Ģäºº

-0.14

quential

-0.14

prar

-0.14

rait

-0.14

hx

-0.14

Ð¾Ð¶

-0.14

imos

-0.14

ocht

-0.13

bir

-0.13

POSITIVE LOGITS

 dere

0.15

ITOR

0.14

AndHashCode

0.13

Wildcard

0.13

 sterile

0.13

 Romeo

0.13

è¿Ļç§į

0.13

-widgets

0.13

ForRow

0.12

Activations Density 0.516%

proper nouns related to people, places, and organizations

No Comments

No Known Activations