INDEX

Explanations

various contextual clues related to locations and identities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

cec

-0.16

agn

-0.15

uesta

-0.15

à¹Ĥà¸¢

-0.15

Ã´n

-0.15

Minimal

-0.15

ÙĦÛĮØ³ÛĮ

-0.15

wend

-0.15

 Minimal

-0.15

FAIL

-0.14

POSITIVE LOGITS

GER

0.17

Zw

0.16

åľŃ

0.16

iqueta

0.15

$($

0.15

ita

0.15

ENG

0.15

å¢

0.14

PUR

0.14

RSA

0.14

Activations Density 0.022%

various contextual clues related to locations and identities

No Comments

No Known Activations