INDEX

Explanations

references to geographical locations or origins in a document

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

bedo

-0.15

zza

-0.14

.struts

-0.14

vida

-0.14

iesz

-0.14

 Rust

-0.14

Ø§ÙĦØ¯

-0.14

eyer

-0.13

frey

-0.13

 desn

-0.13

POSITIVE LOGITS

kup

0.18

_userdata

0.16

 nowhere

0.15

 bench

0.15

seau

0.15

playlist

0.14

bench

0.14

.pool

0.14

pool

0.14

ÐµÐºÑĥ

0.14

Activations Density 0.016%

references to geographical locations or origins in a document

No Comments

No Known Activations