INDEX

Explanations

the word "without" in various contexts, indicating a focus on absence or lack

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

bers

-0.16

avanaugh

-0.15

apiro

-0.14

ichten

-0.14

DAQ

-0.14

egan

-0.14

_DX

-0.13

unda

-0.13

krÃ¡t

-0.13

ea

-0.13

POSITIVE LOGITS

 regard

0.20

 without

0.17

ll

0.16

 necessarily

0.16

iedo

0.16

/by

0.15

paralleled

0.15

 pres

0.15

oji

0.15

 further

0.14

Activations Density 0.042%

the word "without" in various contexts, indicating a focus on absence or lack

No Comments

No Known Activations