INDEX

Explanations

phrases indicating new information or updates

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

kenin

-0.15

ãĥĨãĥ«

-0.14

ulses

-0.14

 endregion

-0.13

laps

-0.13

PLICATE

-0.13

cmds

-0.12

entarios

-0.12

tility

-0.12

atcher

-0.12

POSITIVE LOGITS

erp

0.15

ÂĨ

0.13

achi

0.13

Ñľ

0.13

efa

0.13

á»±

0.12

_CLR

0.12

Ðµ

0.12

pector

0.12

Activations Density 0.362%

phrases indicating new information or updates

No Comments

No Known Activations