INDEX

Explanations

concepts related to nuance and complexity in discussions or descriptions

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

amik

-0.16

sko

-0.15

ean

-0.14

rices

-0.14

ory

-0.14

icus

-0.14

Transformation

-0.14

paired

-0.14

ingu

-0.13

 Transformation

-0.13

POSITIVE LOGITS

jud

0.16

 grad

0.16

-down

0.15

lem

0.14

 Sara

0.14

 versions

0.14

val

0.14

ivol

0.14

utos

0.14

 judgement

0.14

Activations Density 0.043%

concepts related to nuance and complexity in discussions or descriptions

No Comments

No Known Activations