INDEX

Explanations

terms related to biological processes and effects

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

arts

-0.15

oved

-0.14

orda

-0.14

oloj

-0.14

ucc

-0.14

 Hank

-0.14

oud

-0.13

enus

-0.13

Joy

-0.13

POSITIVE LOGITS

kening

0.17

iese

0.16

CRET

0.15

kus

0.15

.Transactional

0.15

elden

0.15

è¿·

0.15

assin

0.14

imers

0.14

 Sabb

0.14

Activations Density 0.079%

terms related to biological processes and effects

No Comments

No Known Activations