INDEX

Explanations

terms related to education and linguistic heritage

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

ritz

-0.17

yon

-0.16

 Bash

-0.14

umen

-0.14

lest

-0.14

ç¦ıåĪ©

-0.14

ëŀĮ

-0.13

olle

-0.13

GameOver

-0.13

iest

-0.13

POSITIVE LOGITS

urette

0.17

ebi

0.15

achu

0.15

ubber

0.15

å½

0.15

CTSTR

0.15

 Walton

0.15

acie

0.14

pod

0.14

Activations Density 0.066%

terms related to education and linguistic heritage

No Comments

No Known Activations