INDEX

Explanations

names and terms related to "Colin" and variations associated with "colon."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

ellung

-0.17

eel

-0.15

_closure

-0.15

 Alcohol

-0.15

sealed

-0.15

phies

-0.15

mÃŃt

-0.15

rike

-0.14

.ham

-0.14

èĩ

-0.14

POSITIVE LOGITS

lected

0.20

col

0.19

apsed

0.18

oured

0.17

Col

0.17

iseum

0.16

(Collectors

0.16

[col

0.15

ijn

0.15

Activations Density 0.059%

names and terms related to "Colin" and variations associated with "colon."

No Comments

No Known Activations