INDEX

Explanations

occurrences of the word "in" and its use 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 @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

otate

-0.15

imensional

-0.14

classpath

-0.14

é¦

-0.14

ÐµÐ½ÑĮ

-0.13

PRINTF

-0.13

.hist

-0.13

ograd

-0.13

ovah

-0.12

 caveat

-0.12

POSITIVE LOGITS

 light

0.35

 response

0.34

 reaction

0.33

 view

0.28

 wake

0.28

response

0.27

 reference

0.26

 answer

0.25

reaction

0.24

light

0.23

Activations Density 0.138%

occurrences of the word "in" and its use in various contexts

No Comments

No Known Activations