INDEX

Explanations

call-to-action phrases and advice related to services or products

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

 frankfurt

-0.15

chos

-0.15

wei

-0.15

urger

-0.14

InitialState

-0.14

 chalk

-0.14

omba

-0.14

yt

-0.14

 Julian

-0.14

azard

-0.14

POSITIVE LOGITS

iger

0.15

 Ð¶Ðµ

0.15

feld

0.14

 therefore

0.14

Ã³ng

0.14

hec

0.14

uez

0.13

 Ø®Ùħ

0.13

igr

0.13

lf

0.13

Activations Density 0.094%

call-to-action phrases and advice related to services or products

No Comments

No Known Activations