INDEX

Explanations

references to locations or contexts within a document

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

agan

-0.15

etti

-0.14

ceiver

-0.14

ummer

-0.14

essor

-0.14

udio

-0.14

ãģ¡ãĤĥãĤĵ

-0.14

 Stub

-0.14

ennes

-0.13

enth

-0.13

POSITIVE LOGITS

aus

0.16

 Lehr

0.15

-archive

0.15

itra

0.15

inci

0.15

Ð»Ð°Ñĩ

0.14

.criteria

0.14

haus

0.14

rio

0.14

à¸ĵà¸ĳ

0.14

Activations Density 0.090%

references to locations or contexts within a document

No Comments

No Known Activations