INDEX

Explanations

statements of opinions or observations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

avic

-0.14

ibold

-0.14

æµħ

-0.14

 details

-0.14

 ones

-0.14

igest

-0.14

 Others

-0.14

mia

-0.13

POSITIVE LOGITS

 missing

0.20

_MISSING

0.17

Missing

0.17

missing

0.17

 Missing

0.16

angstrom

0.14

ifestyles

0.14

 MISSING

0.14

DDL

0.14

 Standing

0.14

Activations Density 0.046%

statements of opinions or observations

No Comments

No Known Activations