INDEX

Explanations

proper nouns related to people and their affiliations or roles in professional contexts

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

antha

-0.18

Ã³st

-0.18

erland

-0.16

illez

-0.16

rowse

-0.16

ÄĽn

-0.15

NÃį

-0.15

CTOR

-0.15

Ð±Ð¾Ð²

-0.14

andon

-0.14

POSITIVE LOGITS

WWW

0.18

 counsel

0.17

etro

0.15

stry

0.14

hip

0.14

 consolidate

0.14

 supplement

0.14

 colored

0.14

get

0.13

 Purpose

0.13

Activations Density 0.276%

proper nouns related to people and their affiliations or roles in professional contexts

No Comments

No Known Activations