INDEX

Explanations

names of individuals or entities, particularly in the context of reviews or critiques

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

ursal

-0.17

 Affero

-0.15

chio

-0.15

odo

-0.14

stub

-0.14

Ã¼lt

-0.14

odon

-0.14

hid

-0.14

_misc

-0.14

afe

-0.14

POSITIVE LOGITS

Äįka

0.17

 Hust

0.16

otine

0.15

ãĥĭãĥ¼

0.14

 Pole

0.14

USIC

0.14

Ã±ana

0.13

Ded

0.13

jet

0.13

mol

0.13

Activations Density 0.007%

names of individuals or entities, particularly in the context of reviews or critiques

No Comments

No Known Activations