INDEX

Explanations

references to annihilation and associated concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

oom

-0.15

oller

-0.15

rips

-0.14

ecta

-0.14

 candid

-0.14

undle

-0.14

ileo

-0.14

icode

-0.14

vida

-0.14

eline

-0.14

POSITIVE LOGITS

hoff

0.18

presso

0.16

atoria

0.14

ahat

0.14

rones

0.13

adoras

0.13

BOSE

0.13

pace

0.13

apo

0.13

zones

0.13

Activations Density 0.166%

references to annihilation and associated concepts

No Comments

No Known Activations