INDEX

Explanations

occurrences of the word "over" in various contexts

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

 posterior

-0.16

oris

-0.15

abel

-0.15

Ãły

-0.14

astic

-0.14

ounters

-0.14

ikon

-0.14

ANE

-0.14

YPE

-0.14

scopic

-0.13

POSITIVE LOGITS

unya

0.16

DOI

0.15

 whom

0.15

ÐµÑĢÑĸ

0.14

-site

0.14

idden

0.14

Î¼Î±ÏĦÎ¿

0.14

å³

0.14

à¸ļà¸Ħ

0.14

Activations Density 0.031%

occurrences of the word "over" in various contexts

No Comments

No Known Activations