INDEX

Explanations

cooking instructions related to heat levels and cooking methods

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

-0.15

cript

-0.14

anton

-0.14

fen

-0.14

ynchronous

-0.14

Arb

-0.14

_FC

-0.13

ÑģÑĤÐ²

-0.13

omba

-0.13

ension

-0.13

POSITIVE LOGITS

 Beaut

0.16

éĺ

0.15

lernen

0.15

iferay

0.14

erview

0.14

aylor

0.14

 Shields

0.14

 ÎĴÎ±Ïĥ

0.13

MOTE

0.13

 sole

0.13

Activations Density 0.012%

cooking instructions related to heat levels and cooking methods

No Comments

No Known Activations