INDEX

Explanations

operations related to updating and manipulating arrays or lists

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

-0.16

ault

-0.15

ho

-0.14

Nob

-0.14

et

-0.14

en

-0.14

vik

-0.13

uria

-0.13

Spr

-0.13

 Catch

-0.13

POSITIVE LOGITS

ï»¿#

0.17

rist

0.16

<quote

0.16

OffsetTable

0.15

alars

0.15

uce

0.15

ILA

0.15

 lesbische

0.14

wick

0.14

//{{

0.14

Activations Density 0.049%

operations related to updating and manipulating arrays or lists

No Comments

No Known Activations