INDEX

Explanations

instances of the word "strike" and its variations related to actions or movements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

ORT

-0.17

indsight

-0.15

mia

-0.15

ÐºÑĢÐ°

-0.15

erals

-0.14

nd

-0.14

istar

-0.14

stoup

-0.14

ĢìĿ´

-0.14

ARGS

-0.14

POSITIVE LOGITS

out

0.24

 strike

0.22

 struck

0.22

 strikes

0.20

 gold

0.20

 Strike

0.20

 Pose

0.18

 chord

0.18

 poses

0.18

Strike

0.18

Activations Density 0.016%

instances of the word "strike" and its variations related to actions or movements

No Comments

No Known Activations