INDEX

Explanations

specific identifiers or attributes related to location and documentation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

Î²Î¬

-0.14

ãĤ¤ãĥ¤

-0.14

rette

-0.14

(Me

-0.14

ataire

-0.14

 Mehmet

-0.14

ela

-0.13

Ĩ

-0.13

izzy

-0.13

veal

-0.13

POSITIVE LOGITS

onds

0.15

ensen

0.15

İ·

0.15

rale

0.14

neys

0.14

à¥įà¤¸à¤°

0.14

orne

0.14

utow

0.14

iac

0.14

_FF

0.13

Activations Density 0.002%

specific identifiers or attributes related to location and documentation

No Comments

No Known Activations