INDEX

Explanations

single words or phrases in a non-Latin script

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

ð

-0.19

inan

-0.16

urn

-0.14

ÃŁ

-0.14

ÅĤy

-0.14

è¾ŀ

-0.13

ð

-0.13

.Suppress

-0.13

ekler

-0.13

upon

-0.13

POSITIVE LOGITS

ÐµÑĢÐ±

0.14

ubber

0.14

isNull

0.14

ameleon

0.14

orgh

0.13

ÑĢÐ¾Ñĩ

0.13

inch

0.13

uler

0.13

 Annex

0.13

ourd

0.13

Activations Density 0.021%

single words or phrases in a non-Latin script

No Comments

No Known Activations