INDEX

Explanations

references to elements in a structured document, such as HTML or XML

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

ãģĦãģ¦

-0.16

ncy

-0.16

-reaching

-0.15

seau

-0.15

ought

-0.15

lea

-0.15

ington

-0.14

jt

-0.14

ff

-0.14

ump

-0.14

POSITIVE LOGITS

plode

0.16

errupted

0.16

 baÅŁÄ±na

0.16

zcze

0.16

 dáº¡ng

0.15

(Element

0.15

heten

0.15

OLON

0.14

Wunused

0.14

=Value

0.14

Activations Density 0.101%

references to elements in a structured document, such as HTML or XML

No Comments

No Known Activations