INDEX

Explanations

occurrences of the letter 'f' 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 @ 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

pto

-0.17

andro

-0.16

ACHI

-0.15

ICollection

-0.14

chers

-0.14

ãĤ·ãĥ§ãĥ³

-0.14

 Spor

-0.14

hton

-0.14

yme

-0.14

Jvm

-0.14

POSITIVE LOGITS

ost

0.26

oment

0.24

ru

0.23

ear

0.22

ailing

0.22

als

0.22

ocusing

0.22

ulfill

0.21

oc

0.21

udging

0.21

Activations Density 0.035%

occurrences of the letter 'f' in various contexts

No Comments

No Known Activations