INDEX

Explanations

occurrences of the word "Fra" and its variations in the text

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

ëł¨

-0.15

éĶ

-0.14

sz

-0.14

antro

-0.14

aver

-0.14

ihn

-0.14

UMAN

-0.14

ÏģÎ¿Ïį

-0.13

_blank

-0.13

ved

-0.13

POSITIVE LOGITS

0.20

cap

0.15

Ã¼stÃ¼

0.15

Äįek

0.15

ps

0.15

czy

0.15

Ã³Å¼

0.15

ZY

0.14

Activations Density 0.008%

occurrences of the word "Fra" and its variations in the text

No Comments

No Known Activations