INDEX

Explanations

words that indicate control, management, or influence over various subjects or actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

ł

-0.15

ife

-0.15

hog

-0.15

lef

-0.14

il

-0.14

ius

-0.14

abin

-0.14

apollo

-0.14

 Creator

-0.14

POSITIVE LOGITS

/type

0.16

omm

0.15

ucz

0.15

 GUIContent

0.15

reesome

0.15

iros

0.14

plied

0.14

edBy

0.14

 Rosenstein

0.14

edException

0.14

Activations Density 0.163%

words that indicate control, management, or influence over various subjects or actions

No Comments

No Known Activations