INDEX

Explanations

references to healthy eating habits

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

quam

-0.18

inner

-0.16

INNER

-0.15

iquement

-0.15

ISON

-0.15

iner

-0.15

wil

-0.15

jedn

-0.15

.ta

-0.15

ÑģÑĤÐ°

-0.15

POSITIVE LOGITS

otten

0.17

andler

0.15

pis

0.15

adil

0.15

 Kevin

0.15

tplib

0.15

ãĥ¼ãĥģ

0.15

ìľ¡

0.15

antha

0.14

Activations Density 0.004%

references to healthy eating habits

No Comments

No Known Activations