INDEX

Explanations

expressions of identity and personal experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

å¤ĩ

-0.18

quil

-0.14

oppins

-0.14

FIG

-0.14

logged

-0.14

ged

-0.13

oned

-0.13

miner

-0.13

/backend

-0.13

ueil

-0.13

POSITIVE LOGITS

 part

0.22

 apart

0.20

 involved

0.19

ieve

0.17

 Î¼ÎŃÏģÎ¿ÏĤ

0.17

 present

0.17

rid

0.16

eline

0.16

 parte

0.16

friend

0.16

Activations Density 0.153%

expressions of identity and personal experiences

No Comments

No Known Activations