INDEX

Explanations

variations of the preposition "för" (meaning "for") in different contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

arias

-0.16

mar

-0.16

aria

-0.15

MOVE

-0.15

Î±Î½Î´

-0.15

 prow

-0.15

-0.14

 Dent

-0.14

fid

-0.14

-live

-0.14

POSITIVE LOGITS

lj

0.29

rf

0.27

ret

0.25

dda

0.24

re

0.24

dd

0.24

rs

0.24

rete

0.23

rl

0.23

rest

0.22

Activations Density 0.007%

variations of the preposition "för" (meaning "for") in different contexts

No Comments

No Known Activations