INDEX

Explanations

information related to personal narratives and experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

enco

-0.17

aal

-0.15

aida

-0.15

aler

-0.15

alle

-0.15

ÐµÐºÑĤÐ¾ÑĢÐ°

-0.14

ihat

-0.14

ECTOR

-0.14

ÑĩÐ¸Ð¼

-0.14

adiens

-0.14

POSITIVE LOGITS

oble

0.15

lest

0.14

çĽĽ

0.14

 Gilles

0.14

ERSIST

0.14

Pal

0.14

 supposedly

0.14

 reportedly

0.13

ngle

0.13

Activations Density 0.249%

information related to personal narratives and experiences

No Comments

No Known Activations