INDEX

Explanations

references to individuals, especially pronouns and possessive forms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

ãĤ¤ãĥ«

-0.17

ascus

-0.15

awan

-0.14

ient

-0.14

.utilities

-0.14

-navbar

-0.14

wan

-0.14

ICO

-0.14

usk

-0.13

stal

-0.13

POSITIVE LOGITS

uby

0.15

tdown

0.15

igy

0.14

 æĻ´

0.14

ÑĥÑĢÐ¸

0.13

ucid

0.13

Ø±Ø§

0.13

ICODE

0.13

erton

0.13

elor

0.13

Activations Density 0.043%

references to individuals, especially pronouns and possessive forms

No Comments

No Known Activations