INDEX

Explanations

forms of the verb "see" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

sel

-0.18

ser

-0.18

thag

-0.17

osh

-0.16

swick

-0.16

ship

-0.16

rec

-0.15

rag

-0.15

sh

-0.15

á»ı

-0.15

POSITIVE LOGITS

idon

0.22

attle

0.22

curity

0.21

ismic

0.20

curities

0.19

ATTLE

0.19

parable

0.18

vier

0.18

lected

0.18

attles

0.17

Activations Density 0.043%

forms of the verb "see" in various contexts

No Comments

No Known Activations