INDEX

Explanations

expressions of auditory perception, particularly the word "sounds" and its variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

anik

-0.17

achu

-0.15

osit

-0.14

ocking

-0.14

 consort

-0.14

 Torch

-0.14

 bodies

-0.13

Gaz

-0.13

âĸ²

-0.13

POSITIVE LOGITS

itzer

0.15

sville

0.15

IPA

0.14

leck

0.14

IME

0.14

ingly

0.14

Malloc

0.14

/feed

0.14

lero

0.14

ancial

0.13

Activations Density 0.012%

expressions of auditory perception, particularly the word "sounds" and its variations

No Comments

No Known Activations