INDEX

Explanations

terms related to options or choices within a context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

Lil

-0.15

ili

-0.14

ÑĸÑĪ

-0.14

 eastern

-0.14

oso

-0.14

cap

-0.14

ulan

-0.13

signature

-0.13

>*</

-0.13

ig

-0.13

POSITIVE LOGITS

 redhead

0.15

/MPL

0.15

 Ð¿Ð°Ð»

0.15

GMEM

0.14

_SEGMENT

0.14

ÑĢÑıÐ´

0.14

abaj

0.14

AGING

0.13

getDisplay

0.13

setWidth

0.13

Activations Density 0.002%

terms related to options or choices within a context

No Comments

No Known Activations