INDEX

Explanations

phrases related to health risks and recurrence

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

-0.15

-0.14

witter

-0.14

 Jacobs

-0.14

sect

-0.14

ni

-0.14

andom

-0.14

uman

-0.13

POSITIVE LOGITS

.opensource

0.14

tone

0.14

_Vector

0.14

elite

0.14

pillar

0.14

REFIX

0.14

pickle

0.14

affen

0.14

cue

0.14

arat

0.14

Activations Density 0.021%

phrases related to health risks and recurrence

No Comments

No Known Activations