INDEX

Explanations

terms related to equivalence or similarity

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

 ActionTypes

-0.15

obre

-0.14

isque

-0.14

ebi

-0.13

egra

-0.13

egan

-0.13

acob

-0.13

rak

-0.13

 ahead

-0.13

ccion

-0.13

POSITIVE LOGITS

 Equivalent

0.17

iez

0.16

 equivalent

0.15

hei

0.15

ritis

0.15

ê³¤

0.15

metatable

0.14

 nhau

0.14

antity

0.14

ison

0.14

Activations Density 0.025%

terms related to equivalence or similarity

No Comments

No Known Activations