INDEX

Explanations

instances of the word "st."

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

ri

-0.17

Ð¾Ð»

-0.17

im

-0.16

yro

-0.16

ojÃŃ

-0.16

ir

-0.16

ORED

-0.16

ÙģØ§Ø¯Ùĩ

-0.15

anje

-0.15

POSITIVE LOGITS

eeper

0.20

udded

0.18

ewart

0.18

oke

0.18

alker

0.17

okes

0.17

ables

0.17

roud

0.17

roller

0.17

ee

0.17

Activations Density 0.010%

instances of the word "st."

No Comments

No Known Activations