INDEX

Explanations

terms related to tourist attractions and points of interest

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

å±ŀ

-0.16

chen

-0.15

ady

-0.15

agini

-0.14

hab

-0.14

atsby

-0.14

ramid

-0.14

iche

-0.14

isson

-0.14

oa

-0.14

POSITIVE LOGITS

utan

0.15

ponge

0.15

Î¿ÏįÏĤ

0.14

0.13

éłħ

0.13

.toObject

0.13

orderby

0.13

Inject

0.13

Activations Density 0.026%

terms related to tourist attractions and points of interest

No Comments

No Known Activations