INDEX

Explanations

references to obtaining or interacting with water

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

unker

-0.18

chio

-0.17

aro

-0.16

ulumi

-0.16

aus

-0.16

ATCH

-0.15

anco

-0.14

oS

-0.14

 Banc

-0.14

POSITIVE LOGITS

(IConfiguration

0.14

FRING

0.14

èģ

0.14

ittest

0.14

 stores

0.13

tsx

0.13

ÐµÐ½Ñĥ

0.13

 fing

0.13

stores

0.13

Activations Density 0.283%

references to obtaining or interacting with water

No Comments

No Known Activations