INDEX

Explanations

terms related to evaluations or appraisals

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

 Liberation

-0.17

ansi

-0.16

 occasions

-0.14

decltype

-0.14

 decltype

-0.14

cko

-0.14

ãĥĥãĤ·ãĥ¥

-0.14

iri

-0.13

Mess

-0.13

POSITIVE LOGITS

amet

0.18

rive

0.15

ingleton

0.14

LayoutConstraint

0.14

ITHER

0.14

vern

0.13

 sudden

0.13

OffsetTable

0.13

GN

0.13

OWER

0.13

Activations Density 0.008%

terms related to evaluations or appraisals

No Comments

No Known Activations