INDEX

Explanations

terms related to action and engagement in various contexts

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

gone

-0.16

usto

-0.16

aldo

-0.16

 wound

-0.15

INTR

-0.15

jl

-0.15

Åº

-0.14

raud

-0.14

jure

-0.14

ÏģÎµÏħ

-0.14

POSITIVE LOGITS

nist

0.15

0.14

aled

0.14

onet

0.14

 Olson

0.14

 Sommer

0.14

 ?><?

0.13

Jos

0.13

Ð²Ð°Ð¶Ð°

0.13

Activations Density 0.206%

terms related to action and engagement in various contexts

No Comments

No Known Activations