INDEX

Explanations

central or significant entities or concepts within the text

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

ãĤ¦ãĤ¹

-0.16

/language

-0.15

essel

-0.15

inand

-0.15

qx

-0.15

ÏĨÎ¹

-0.15

chio

-0.14

ItemClick

-0.14

orum

-0.14

POSITIVE LOGITS

stay

0.22

/Main

0.16

most

0.16

AxisSize

0.15

-purpose

0.15

ardi

0.15

íģ¼

0.15

egend

0.15

eah

0.14

/main

0.14

Activations Density 0.040%

central or significant entities or concepts within the text

No Comments

No Known Activations