INDEX

Explanations

terms related to self-awareness and self-regulation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

ainment

-0.15

rh

-0.14

ional

-0.14

ket

-0.14

pus

-0.14

length

-0.14

usp

-0.14

ibraltar

-0.14

alat

-0.14

oning

-0.14

POSITIVE LOGITS

/self

0.24

-self

0.19

SELF

0.18

 self

0.18

 Self

0.18

Self

0.17

Ã¤nd

0.16

(Self

0.16

ugg

0.15

ercul

0.15

Activations Density 0.026%

terms related to self-awareness and self-regulation

No Comments

No Known Activations