INDEX

Explanations

references to personal states of being and neglect

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

blo

-0.15

 Hast

-0.15

allas

-0.14

<<<

-0.14

xffff

-0.13

 Brewery

-0.13

outine

-0.13

ÏįÎ½

-0.13

mh

-0.13

_Runtime

-0.13

POSITIVE LOGITS

elsen

0.15

zbek

0.15

zet

0.14

ortho

0.14

peg

0.14

neau

0.14

afia

0.14

Compiler

0.14

Py

0.14

ace

0.14

Activations Density 0.155%

references to personal states of being and neglect

No Comments

No Known Activations