INDEX

Explanations

references to personal pronouns and the expressions of personal opinions or states of being

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

å¾Ĵ

-0.15

å¸¯

-0.14

rio

-0.14

/Branch

-0.14

_HS

-0.14

aghan

-0.14

erten

-0.13

auf

-0.13

ril

-0.13

vÄĽÅĻ

-0.13

POSITIVE LOGITS

uddle

0.17

ette

0.14

etsk

0.14

Lum

0.14

SCRIPTION

0.14

Zuk

0.13

 versa

0.13

liÄŁine

0.13

ABCDE

0.13

Activations Density 0.241%

references to personal pronouns and the expressions of personal opinions or states of being

No Comments

No Known Activations