INDEX

Explanations

occurrences of the word "touring" and related forms

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

enton

-0.15

agos

-0.14

aker

-0.14

wick

-0.14

EVER

-0.14

gom

-0.13

(Card

-0.13

ikes

-0.13

/Card

-0.13

ackbar

-0.13

POSITIVE LOGITS

 <!--[

0.16

Ð°Ð»ÐµÐ¶

0.15

ograd

0.15

ephir

0.15

rok

0.14

 ÏĦÎ¬

0.14

 chaud

0.14

 {{--<

0.14

Î²Î¿Î»

0.14

 MÃľ

0.14

Activations Density 0.004%

occurrences of the word "touring" and related forms

No Comments

No Known Activations