INDEX

Explanations

references to companies or organizations in a business context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

 Podesta

-0.17

ghest

-0.17

hiba

-0.16

andin

-0.16

erce

-0.16

_ATOMIC

-0.16

ascar

-0.15

abbo

-0.15

 Imported

-0.15

onomy

-0.15

POSITIVE LOGITS

 Group

0.18

 Medium

0.17

etal

0.16

ju

0.16

 competence

0.16

 Segment

0.16

Ø±ÙĪØ¨

0.16

umba

0.16

axon

0.15

 Neck

0.15

Activations Density 0.069%

references to companies or organizations in a business context

No Comments

No Known Activations