INDEX

Explanations

phrases that indicate exceptions or special conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

yne

-0.15

liers

-0.15

uh

-0.15

ere

-0.15

HEET

-0.14

otta

-0.14

achten

-0.14

.gs

-0.14

 Farr

-0.14

eyh

-0.14

POSITIVE LOGITS

pell

0.17

 ******************************************************************************/↵

0.15

abbage

0.14

rench

0.14

engo

0.14

à¥ĩà¤Ĥ,

0.14

rem

0.14

è®®

0.13

bookmark

0.13

aaS

0.13

Activations Density 0.229%

phrases that indicate exceptions or special conditions

No Comments

No Known Activations