INDEX

Explanations

the word "straight" used in various contexts, indicating a focus on directness or lack of deviation

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

sein

-0.20

rÃ¡l

-0.16

imeter

-0.16

å¹ħ

-0.15

atomy

-0.15

chief

-0.15

munition

-0.14

ikan

-0.14

mits

-0.14

RIORITY

-0.14

POSITIVE LOGITS

-ÑĤÐ°ÐºÐ¸

0.19

ness

0.19

iddy

0.18

zeitig

0.17

er

0.16

ãĥ³ãĥĩ

0.16

LTR

0.15

rottle

0.15

rown

0.15

um

0.14

Activations Density 0.024%

the word "straight" used in various contexts, indicating a focus on directness or lack of deviation

No Comments

No Known Activations