INDEX

Explanations

negations or contradictions in statements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

iscard

-0.15

PLAIN

-0.14

aru

-0.14

ses

-0.13

rian

-0.13

isha

-0.13

ional

-0.13

 tribunal

-0.13

 Klopp

-0.13

``

-0.13

POSITIVE LOGITS

psz

0.17

apot

0.16

eft

0.16

ÙĦØ³

0.16

aroo

0.14

 remot

0.14

ept

0.14

enstein

0.14

 Emerson

0.14

ymb

0.14

Activations Density 0.094%

negations or contradictions in statements

No Comments

No Known Activations